Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It usefully discloses that it reads the *last* audit's data and describes the return payload (clusters/silos, silo source menu-or-link, silo_assign diagnostics, anomaly counts), but it does not state whether it is a read-only operation, whether it can trigger recomputation, or any permission/side-effect behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences, front-loaded with the resource and its payload. The field enumeration is list-like and efficient, though the parenthetical detail (url, in/out link, word_count) is somewhat verbose for a description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description fills the gap by enumerating the returned structures (summary, cluster/silo, diagnostics, anomaly counts) and explaining multilingual handling. It stops short of clarifying project_id and read/write semantics, which for a read tool is a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33%, so the description must compensate. It explains the `view` enum modes (auto default with AI fallback, structural, ai) which the schema leaves undocumented, and it clarifies that `lang` (drawn from summary.langs) restricts the entire result to one language. Only project_id remains unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource ('Topical architecture dell'ultimo audit') and enumerates exactly what it returns (summary, cluster/silo with pillar, link counts, silo source, silo_assign diagnostics, anomaly counts). It does not differentiate itself from close siblings like get_topical_anomalies or refine_topical_architecture, even though it mentions 'conteggi anomalie'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use guidance or routing to alternatives. The only usage-adjacent content is the explanation of the `view` default ('auto, AI se disponibile') and the `lang` filtering behavior, which clarifies modes rather than when this tool should be chosen over siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.